# nolint start
library(mlexperiments)
library(mllrnrs)
The hardware and bandwidth for this mirror is donated by METANET, the Webhosting and Full Service-Cloud Provider.
If you wish to report a bug, or if you are interested in having us mirror your free-software or open-source project, please feel free to contact us at mirror[@]metanet.ch.
# nolint start
library(mlexperiments)
library(mllrnrs)
See https://github.com/kapsner/mllrnrs/blob/main/R/learner_glmnet.R for implementation details.
library(mlbench)
data("DNA")
<- DNA |>
dataset ::as.data.table() |>
data.tablena.omit()
<- colnames(dataset)[160:180]
feature_cols <- "Class" target_col
<- 123
seed if (isTRUE(as.logical(Sys.getenv("_R_CHECK_LIMIT_CORES_")))) {
# on cran
<- 2L
ncores else {
} <- ifelse(
ncores test = parallel::detectCores() > 4,
yes = 4L,
no = ifelse(
test = parallel::detectCores() < 2L,
yes = 1L,
no = parallel::detectCores()
)
)
}options("mlexperiments.bayesian.max_init" = 10L)
<- splitTools::partition(
data_split y = dataset[, get(target_col)],
p = c(train = 0.7, test = 0.3),
type = "stratified",
seed = seed
)
<- model.matrix(
train_x ~ -1 + .,
$train, .SD, .SDcols = feature_cols]
dataset[data_split
)<- dataset[data_split$train, get(target_col)]
train_y
<- model.matrix(
test_x ~ -1 + .,
$test, .SD, .SDcols = feature_cols]
dataset[data_split
)<- dataset[data_split$test, get(target_col)] test_y
<- splitTools::create_folds(
fold_list y = train_y,
k = 3,
type = "stratified",
seed = seed
)
# required learner arguments, not optimized
<- list(
learner_args family = "multinomial",
type.measure = "class",
standardize = TRUE
)
# set arguments for predict function and performance metric,
# required for mlexperiments::MLCrossValidation and
# mlexperiments::MLNestedCV
<- list(type = "response", reshape = TRUE)
predict_args <- metric("bacc")
performance_metric <- NULL
performance_metric_args <- FALSE
return_models
# required for grid search and initialization of bayesian optimization
<- expand.grid(
parameter_grid alpha = seq(0, 1, 0.05)
)# reduce to a maximum of 10 rows
if (nrow(parameter_grid) > 10) {
set.seed(123)
<- sample(seq_len(nrow(parameter_grid)), 10, FALSE)
sample_rows <- kdry::mlh_subset(parameter_grid, sample_rows)
parameter_grid
}
# required for bayesian optimization
<- list(
parameter_bounds alpha = c(0., 1.)
)<- list(
optim_args iters.n = ncores,
kappa = 3.5,
acq = "ucb"
)
<- mlexperiments::MLTuneParameters$new(
tuner learner = mllrnrs::LearnerGlmnet$new(
metric_optimization_higher_better = FALSE
),strategy = "grid",
ncores = ncores,
seed = seed
)
$parameter_grid <- parameter_grid
tuner$learner_args <- learner_args
tuner$split_type <- "stratified"
tuner
$set_data(
tunerx = train_x,
y = train_y
)
<- tuner$execute(k = 3)
tuner_results_grid #>
#> Parameter settings [==================>-----------------------------------------------------------------------------] 2/10 ( 20%)
#> Parameter settings [============================>-------------------------------------------------------------------] 3/10 ( 30%)
#> Parameter settings [=====================================>----------------------------------------------------------] 4/10 ( 40%)
#> Parameter settings [===============================================>------------------------------------------------] 5/10 ( 50%)
#> Parameter settings [=========================================================>--------------------------------------] 6/10 ( 60%)
#> Parameter settings [==================================================================>-----------------------------] 7/10 ( 70%)
#> Parameter settings [============================================================================>-------------------] 8/10 ( 80%)
#> Parameter settings [=====================================================================================>----------] 9/10 ( 90%)
#> Parameter settings [===============================================================================================] 10/10 (100%)
head(tuner_results_grid)
#> setting_id metric_optim_mean lambda alpha family type.measure standardize
#> 1: 1 0.4728578 0.003092562 0.70 multinomial class TRUE
#> 2: 2 0.4737550 0.002639842 0.90 multinomial class TRUE
#> 3: 3 0.4733064 0.003330451 0.65 multinomial class TRUE
#> 4: 4 0.4733064 0.017972493 0.10 multinomial class TRUE
#> 5: 5 0.4733064 0.003993887 0.45 multinomial class TRUE
#> 6: 6 0.4728578 0.022574498 0.05 multinomial class TRUE
<- mlexperiments::MLTuneParameters$new(
tuner learner = mllrnrs::LearnerGlmnet$new(
metric_optimization_higher_better = FALSE
),strategy = "bayesian",
ncores = ncores,
seed = seed
)
$parameter_grid <- parameter_grid
tuner$parameter_bounds <- parameter_bounds
tuner
$learner_args <- learner_args
tuner$optim_args <- optim_args
tuner
$split_type <- "stratified"
tuner
$set_data(
tunerx = train_x,
y = train_y
)
<- tuner$execute(k = 3)
tuner_results_bayesian #>
#> Registering parallel backend using 4 cores.
head(tuner_results_bayesian)
#> Epoch setting_id alpha gpUtility acqOptimum inBounds Elapsed Score metric_optim_mean lambda errorMessage family
#> 1: 0 1 0.70 NA FALSE TRUE 1.666 -0.4728578 0.4728578 0.003092562 NA multinomial
#> 2: 0 2 0.90 NA FALSE TRUE 1.635 -0.4737550 0.4737550 0.002639842 NA multinomial
#> 3: 0 3 0.65 NA FALSE TRUE 1.657 -0.4733064 0.4733064 0.003330451 NA multinomial
#> 4: 0 4 0.10 NA FALSE TRUE 1.744 -0.4733064 0.4733064 0.017972493 NA multinomial
#> 5: 0 5 0.45 NA FALSE TRUE 0.577 -0.4733064 0.4733064 0.003993887 NA multinomial
#> 6: 0 6 0.05 NA FALSE TRUE 0.687 -0.4728578 0.4728578 0.022574498 NA multinomial
#> type.measure standardize
#> 1: class TRUE
#> 2: class TRUE
#> 3: class TRUE
#> 4: class TRUE
#> 5: class TRUE
#> 6: class TRUE
<- mlexperiments::MLCrossValidation$new(
validator learner = mllrnrs::LearnerGlmnet$new(
metric_optimization_higher_better = FALSE
),fold_list = fold_list,
ncores = ncores,
seed = seed
)
$learner_args <- tuner$results$best.setting[-1]
validator
$predict_args <- predict_args
validator$performance_metric <- performance_metric
validator$performance_metric_args <- performance_metric_args
validator$return_models <- return_models
validator
$set_data(
validatorx = train_x,
y = train_y
)
<- validator$execute()
validator_results #>
#> CV fold: Fold1
#>
#> CV fold: Fold2
#>
#> CV fold: Fold3
head(validator_results)
#> fold performance alpha lambda family type.measure standardize
#> 1: Fold1 0.3672581 0.7 0.003092562 multinomial class TRUE
#> 2: Fold2 0.3524351 0.7 0.003092562 multinomial class TRUE
#> 3: Fold3 0.3700659 0.7 0.003092562 multinomial class TRUE
<- mlexperiments::MLNestedCV$new(
validator learner = mllrnrs::LearnerGlmnet$new(
metric_optimization_higher_better = FALSE
),strategy = "grid",
fold_list = fold_list,
k_tuning = 3L,
ncores = ncores,
seed = seed
)
$parameter_grid <- parameter_grid
validator$learner_args <- learner_args
validator$split_type <- "stratified"
validator
$predict_args <- predict_args
validator$performance_metric <- performance_metric
validator$performance_metric_args <- performance_metric_args
validator$return_models <- return_models
validator
$set_data(
validatorx = train_x,
y = train_y
)
<- validator$execute()
validator_results #>
#> CV fold: Fold1
#>
#> Parameter settings [==================>-----------------------------------------------------------------------------] 2/10 ( 20%)
#> Parameter settings [============================>-------------------------------------------------------------------] 3/10 ( 30%)
#> Parameter settings [=====================================>----------------------------------------------------------] 4/10 ( 40%)
#> Parameter settings [===============================================>------------------------------------------------] 5/10 ( 50%)
#> Parameter settings [=========================================================>--------------------------------------] 6/10 ( 60%)
#> Parameter settings [==================================================================>-----------------------------] 7/10 ( 70%)
#> Parameter settings [============================================================================>-------------------] 8/10 ( 80%)
#> Parameter settings [=====================================================================================>----------] 9/10 ( 90%)
#> Parameter settings [===============================================================================================] 10/10 (100%)
#> CV fold: Fold2
#> CV progress [====================================================================>-----------------------------------] 2/3 ( 67%)
#>
#> Parameter settings [==================>-----------------------------------------------------------------------------] 2/10 ( 20%)
#> Parameter settings [============================>-------------------------------------------------------------------] 3/10 ( 30%)
#> Parameter settings [=====================================>----------------------------------------------------------] 4/10 ( 40%)
#> Parameter settings [===============================================>------------------------------------------------] 5/10 ( 50%)
#> Parameter settings [=========================================================>--------------------------------------] 6/10 ( 60%)
#> Parameter settings [==================================================================>-----------------------------] 7/10 ( 70%)
#> Parameter settings [============================================================================>-------------------] 8/10 ( 80%)
#> Parameter settings [=====================================================================================>----------] 9/10 ( 90%)
#> Parameter settings [===============================================================================================] 10/10 (100%)
#> CV fold: Fold3
#> CV progress [========================================================================================================] 3/3 (100%)
#>
#> Parameter settings [==================>-----------------------------------------------------------------------------] 2/10 ( 20%)
#> Parameter settings [============================>-------------------------------------------------------------------] 3/10 ( 30%)
#> Parameter settings [=====================================>----------------------------------------------------------] 4/10 ( 40%)
#> Parameter settings [===============================================>------------------------------------------------] 5/10 ( 50%)
#> Parameter settings [=========================================================>--------------------------------------] 6/10 ( 60%)
#> Parameter settings [==================================================================>-----------------------------] 7/10 ( 70%)
#> Parameter settings [============================================================================>-------------------] 8/10 ( 80%)
#> Parameter settings [=====================================================================================>----------] 9/10 ( 90%)
#> Parameter settings [===============================================================================================] 10/10 (100%)
head(validator_results)
#> fold performance lambda alpha family type.measure standardize
#> 1: Fold1 0.3465038 0.006548214 0.90 multinomial class TRUE
#> 2: Fold2 0.3475436 0.001710793 0.65 multinomial class TRUE
#> 3: Fold3 0.3514970 0.038236018 0.10 multinomial class TRUE
<- mlexperiments::MLNestedCV$new(
validator learner = mllrnrs::LearnerGlmnet$new(
metric_optimization_higher_better = FALSE
),strategy = "bayesian",
fold_list = fold_list,
k_tuning = 3L,
ncores = ncores,
seed = 312
)
$parameter_grid <- parameter_grid
validator$learner_args <- learner_args
validator$split_type <- "stratified"
validator
$parameter_bounds <- parameter_bounds
validator$optim_args <- optim_args
validator
$predict_args <- predict_args
validator$performance_metric <- performance_metric
validator$performance_metric_args <- performance_metric_args
validator$return_models <- TRUE
validator
$set_data(
validatorx = train_x,
y = train_y
)
<- validator$execute()
validator_results #>
#> CV fold: Fold1
#>
#> Registering parallel backend using 4 cores.
#>
#> CV fold: Fold2
#> CV progress [====================================================================>-----------------------------------] 2/3 ( 67%)
#>
#> Registering parallel backend using 4 cores.
#>
#> CV fold: Fold3
#> CV progress [========================================================================================================] 3/3 (100%)
#>
#> Registering parallel backend using 4 cores.
head(validator_results)
#> fold performance alpha lambda family type.measure standardize
#> 1: Fold1 0.3652609 0.7000000 0.004817737 multinomial class TRUE
#> 2: Fold2 0.3416288 0.4178147 0.017108341 multinomial class TRUE
#> 3: Fold3 0.3467740 0.1000000 0.041963982 multinomial class TRUE
<- mlexperiments::predictions(
preds_glmnet object = validator,
newdata = test_x
)
<- mlexperiments::performance(
perf_glmnet object = validator,
prediction_results = preds_glmnet,
y_ground_truth = test_y
)
perf_glmnet#> model performance
#> 1: Fold1 0.3606304
#> 2: Fold2 0.3603913
#> 3: Fold3 0.3529292
Here, glmnet
’s weights
-argument is used to rescale the case-weights during the training.
# define the target weights
<- ifelse(train_y == "n", 0.8, ifelse(train_y == "ei", 1.2, 1))
y_weights head(y_weights)
#> [1] 1.2 1.2 0.0 0.8 0.8 0.0
<- mlexperiments::MLTuneParameters$new(
tuner_w_weights learner = mllrnrs::LearnerGlmnet$new(
metric_optimization_higher_better = FALSE
),strategy = "grid",
ncores = ncores,
seed = seed
)
$parameter_grid <- parameter_grid
tuner_w_weights$learner_args <- c(
tuner_w_weights
learner_args,list(case_weights = y_weights)
)$split_type <- "stratified"
tuner_w_weights
$set_data(
tuner_w_weightsx = train_x,
y = train_y
)
<- tuner_w_weights$execute(k = 3)
tuner_results_grid #>
#> Parameter settings [============================>-------------------------------------------------------------------] 3/10 ( 30%)
#> Parameter settings [=====================================>----------------------------------------------------------] 4/10 ( 40%)
#> Parameter settings [===============================================>------------------------------------------------] 5/10 ( 50%)
#> Parameter settings [=========================================================>--------------------------------------] 6/10 ( 60%)
#> Parameter settings [==================================================================>-----------------------------] 7/10 ( 70%)
#> Parameter settings [============================================================================>-------------------] 8/10 ( 80%)
#> Parameter settings [=====================================================================================>----------] 9/10 ( 90%)
#> Parameter settings [===============================================================================================] 10/10 (100%)
head(tuner_results_grid)
#> setting_id metric_optim_mean lambda alpha family type.measure standardize
#> <int> <num> <num> <num> <char> <char> <lgcl>
#> 1: 1 0.5428029 0.015786209 0.70 multinomial class TRUE
#> 2: 2 0.5410926 0.005314924 0.90 multinomial class TRUE
#> 3: 3 0.5425178 0.017000533 0.65 multinomial class TRUE
#> 4: 4 0.5429929 0.027372552 0.10 multinomial class TRUE
#> 5: 5 0.5422328 0.020387093 0.45 multinomial class TRUE
#> 6: 6 0.5428979 0.034381521 0.05 multinomial class TRUE
<- mlexperiments::MLCrossValidation$new(
validator learner = mllrnrs::LearnerGlmnet$new(
metric_optimization_higher_better = FALSE
),fold_list = fold_list,
ncores = ncores,
seed = seed
)
# append the optimized setting from above with the newly created weights
$learner_args <- c(
validator$results$best.setting[-1],
tunerlist("case_weights" = y_weights)
)
$predict_args <- predict_args
validator$performance_metric <- performance_metric
validator$performance_metric_args <- performance_metric_args
validator$return_models <- return_models
validator
$set_data(
validatorx = train_x,
y = train_y
)
<- validator$execute()
validator_results #>
#> CV fold: Fold1
#>
#> CV fold: Fold2
#>
#> CV fold: Fold3
#> CV progress [========================================================================================================] 3/3 (100%)
#>
head(validator_results)
#> fold performance alpha lambda family type.measure standardize
#> <char> <num> <num> <num> <char> <char> <lgcl>
#> 1: Fold1 0.4139240 0.7 0.003092562 multinomial class TRUE
#> 2: Fold2 0.3570648 0.7 0.003092562 multinomial class TRUE
#> 3: Fold3 0.3831881 0.7 0.003092562 multinomial class TRUE
These binaries (installable software) and packages are in development.
They may not be fully stable and should be used with caution. We make no claims about them.